Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 989 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.5756. Min Act: -0.0002

Data Index: 337333 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4624. Min Act: -0.0002

Data Index: 128811 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.5043. Min Act: -0.0002

Data Index: 1282831 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4389. Min Act: -0.0002

Data Index: 854321 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3997. Min Act: -0.0002

Data Index: 728762 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4896. Min Act: -0.0002

Data Index: 1044557 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4799. Min Act: -0.0002

Data Index: 178933 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4787. Min Act: -0.0002

Data Index: 1193846 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4787. Min Act: -0.0002

Data Index: 759763 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4739. Min Act: -0.0002

Data Index: 89112 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4143. Min Act: -0.0002

Data Index: 124239 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4564. Min Act: -0.0002

Data Index: 1085876 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4511. Min Act: -0.0002

Data Index: 1231630 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4548. Min Act: -0.0002

Data Index: 645984 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4695. Min Act: -0.0002

Data Index: 1346206 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4558. Min Act: -0.0002

Data Index: 59610 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.3944. Min Act: -0.0002

Data Index: 244034 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4447. Min Act: -0.0002

Data Index: 88568 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4942. Min Act: -0.0002

Data Index: 76343 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.5756. Min Range: -0.5756

Max Act: 0.4961. Min Act: -0.0002

Data Index: 808649 (C4 (Web Text))

Max Activating Token Index: 4